EUVIMEDEUVIMED entdecken
Crossref

Multi-Stage Robust Federated Learning: Addressing Label Noise under Data Heterogeneity and Imbalance

Kaibo Wang, Anqi Zhang, Tangyou Liu, Wenqian Zhang, Guanglin Zhang

ACM Transactions on Intelligent Systems and Technology · 31.08.2026 · 17 (4) · 1-22

DOI: 10.1145/3800941 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 28.04.2026. Verfasst von Kaibo Wang und 4 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shanghai Institutions of Higher Learning, the Science and Technology Commission of Shanghai Municipality, Chenguang Program of Shanghai Education Development Foundation and Shanghai Municipal Education Commission.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated Learning (FL) enables collaborative model training while preserving data privacy, but the presence of noisy labels in local datasets remains a significant challenge, particularly under heterogeneous noise conditions and class imbalance. In this work, we introduce a novel Multi-Stage Robust Federated Learning (MRFL) framework to address these issues. In the warm-up noise detection stage, MRFL computes per-class average losses on each client and employs a Gaussian mixture model to accurately identify clients with substantial label noise. In the subsequent noise-robust training stage, a robust loss function and noise solver are designed to distinguish clean from noisy samples, while semi-supervised learning is used to recover valuable information from tail classes. Moreover, a robust weighted aggregation strategy is adopted to mitigate the adverse effects of noisy clients. Extensive experiments on CIFAR-10/100-LT and ICH datasets demonstrate that MRFL outperforms state-of-the-art methods in federated noisy label learning scenarios characterized by data heterogeneity and imbalance.

Förderung

  • National Natural Science Foundation of China
  • Shanghai Institutions of Higher Learning, the Science and Technology Commission of Shanghai Municipality
  • Chenguang Program of Shanghai Education Development Foundation and Shanghai Municipal Education Commission
  • AI-Enhanced Research Program of Shanghai Municipal Education Commission
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Wang, K., Zhang, A., Liu, T., Zhang, W., & Zhang, G. (2026). Multi-Stage Robust Federated Learning: Addressing Label Noise under Data Heterogeneity and Imbalance. ACM Transactions on Intelligent Systems and Technology, 17(4), 1-22. https://doi.org/10.1145/3800941

Vancouver

Wang K, Zhang A, Liu T, Zhang W, Zhang G. Multi-Stage Robust Federated Learning: Addressing Label Noise under Data Heterogeneity and Imbalance. ACM Transactions on Intelligent Systems and Technology. 2026;17(4):1-22. doi:10.1145/3800941

BibTeX
@article{Wang2026,
  author = {Wang, Kaibo and Zhang, Anqi and Liu, Tangyou and Zhang, Wenqian and Zhang, Guanglin},
  title = {Multi-Stage Robust Federated Learning: Addressing Label Noise under Data Heterogeneity and Imbalance},
  journal = {ACM Transactions on Intelligent Systems and Technology},
  year = {2026},
  volume = {17},
  number = {4},
  pages = {1--22},
  doi = {10.1145/3800941}
}
Kostenlos starten →